Suppose you pick ten slips of paper from the top of the jar. Do all names have an equal
chance of being selected? Maybe the slips at the top belong to the last class that put their
names in the jar. Selecting from the top does not give the names at the bottom of the jar an
equal chance. This would be a biased sample because it does not represent the whole
population.
Suppose, instead, that you put your hand in and mix the slips all around. You do this each
time you pick the ten names. With this method, all names get an equal chance of being
selected. This would be a random sample.
Here are some ways to select a representative random sample.
• Use a pattern, such as selecting every fourth person who enters the cafeteria.
• Use a method, such as drawing names out of a hat, where everyone has an equal chance
of being selected.
• Divide the population into groups, such as by grade level, and randomly select people
from each group.
Here are some ways of selecting a sample that might result in a biased sample.
• Let people volunteer to take a survey.
• Choose people who are easy to reach, such as the students who happen to be in the
cafeteria when you are available to give surveys.
• Choose people as a group, such as students on the honor roll.
Think How can you use data collected from a random sample?
You can use data from a random sample to generalize about a population. Maybe about half
of the students in the sample say that pizza is their favorite school lunch. You might predict
that about half the population has the same preference. The data collected from the sample
might be used for making menu choices and for determining food orders.
Reflect
1 What do you think would be a good way to select a random sample of all the students at
the 12 schools in the school district mentioned on the previous page?